Plugins

MCP server management panel in Settings: add, edit, enable/disable and delete servers across user and workspace scopes with form or JSON editing, and auto-register discovered MCP tools as native conversation tools.

Five web UI tools in one plugin: a provider + model two-button selector with reasoning-level control, collapse/expand-all for sidebar workspace groups, a session tab listing the files the session changed (needs kernel 0.1.2-alpha.1+, silently absent on older kernels), a workspace badge next to the session title, and a settings page that toggles them.

Persistent project intelligence and memory plugin for DSH: architecture analysis, cross-session context, TODOs, and optional hybrid retrieval

DeepSeek Harness plugin for organizing AI discussions into research topics, traceable knowledge cards, and reusable research materials on an interactive graph

Stores bookmarks as local Markdown files in a folder you choose, with a sidebar page for collections and links, library-wide search, automatic favicon downloads, and three agent tools.

Agent-native API client for DeepSeek Harness: Postman-like debugging UI (request tree with context menus and full keyboard navigation, resizable sidebar, layered auto-generated header preview with per-item suppression and constant secret masking), six api_client_* agent tools sharing the same request core, redaction and audit chain with the human UI, Postman Collection v2.1 import with a migration report, environment variables with SecretRef indirection, and a fail-closed SSRF network policy.

Polaris Memory: local-first project memory plugin for DeepSeek Harness. Uses per-project .dsh-memory.json; provides memory_read/recall/write/update/delete tools, /memory command and settings UI, with tiered injection (resident user profile + scene-triggered memories with P1/P2/P3 importance), semantic recall (IDF + synonym layer), and a hard-guard mechanism for bottom-line memories (detect deny-semantics -> authorize -> block AI deletion; user can confirm-override).

A focused end-user QA surface backed by native DeepSeek Harness sessions

Automatic model-tier routing for DeepSeek Harness: one user instruction enters, one tier decision comes out — complex intent is planned on the strong tier and implemented on the cheap tier, simple intent stays cheap throughout, with a deterministic guard and a TTL escalation fallback.

Hash-anchored file tools for DeepSeek Harness: the read, edit, write and grep tools are replaced by versions where every line is addressed by a variable-length content anchor instead of a line number, and the plugin also registers delete, rename, undo_last_edit, ast_grep, ast_edit, lsp and format. Edits answer with a unified diff; a stale or ambiguous anchor is rejected and a fresh one served back; undo survives restarts; structural search and rewrite run on tree-sitter and semantic work through a language server; a bundled web card plugin renders read, diff, grep and LSP cards from the tools' own structured metadata.

SSH session manager for DeepSeek Harness: saved profiles, agent ssh_run, interactive terminals, and SFTP with secrets kept in the DSH credential center.

Compares existing DSH sessions or runs controlled A/B trials between agent presets, showing aligned timelines, paired metric deltas, explicit success checks, and exportable reports.

Adds a Canvas drawer and eight model tools to create, patch, version, and export HTML, Markdown, Mermaid, SVG, and React artifacts.

Open folders on remote hosts over SSH as Harness workspaces: file tools (read/write/edit/grep/glob) and shell commands run directly on the remote host over SFTP, ripgrep, and ssh2 exec, with no local mirroring, an encrypted multi-host registry, and the local sandbox policy still enforced.

DSH GitHub connector: review PRs, triage issues, debug CI, prepare changes (18 tools, gh-first + REST fallback, approval-gated writes).

Capture selected DSH, local MCP, or native WebMCP calls as reviewed, parameterized routines, expose typed tools, and replay with fresh approval.

Task kanban where agents claim and hand off work through taskboard_* tools, which cannot move a task to done or canceled — acceptance stays with a human.

BaziDIY ontology plugin: deterministic bazi/wuxing/bead/style rules as DSH tools (calculate_bazi, propose_designs, generate_design, save_design, load_design), plus bracelet SVG rendering and a bead editor; no LLM calls inside execute.

DSH environment management: auto-installs a Rust/Tauri desktop host (downloaded per-OS from dsh-desktop-host releases, source build as fallback), one-click runtime updates, Windows platform compatibility, official DeepSeek billing, and a built-in code editor for the workspace.

Settings-page manager for archived DeepSeek Harness sessions: restore an archived session to its previous workspace position or permanently delete it (direct physical deletion, no backup layer). Adds a red permanently-delete item to the session context menu and three agent tools. Deleting an open session works immediately; the leftover in-memory copy is hidden behind an archive tombstone until the next restart.

Custom script manager for DSH: turn verified operations into reusable scripts that run directly via /script or register as agent tools, with parameterized scripts, declared expected outcomes, and execution history.

基于 SenseVoiceSmall（iic/SenseVoiceSmall）多语言语音理解模型的 DSH Desktop 本地语音输入插件。

“What should we build next?” There’s a skill for that.

Actionable quality diagnostics for DSH agent sessions, with tool-call evidence and next-step recommendations.